| What it does | See which AI agents use your product, where they fail, and what to fix
| Fix your AI agent while it's still running
|
|---|
| Stage | Startup
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Free trial
| Free
|
|---|
| Pricing | Free trial for 14 days. Starter: $15/month (2 projects, 50k events/month, 30-day retention). Growth: $49/month (5 projects, 500k events/month, 90-day retention, up to 5 team members). Scale: $149/month (25 projects, 5M events/month, 1-year retention, unlimited team members).
| Free account for Circuit and Jack. The debugger is free and open source under MIT license.
|
|---|
| Key features | - Monitor AI crawlers, website agents, MCP clients, APIs and CLIs
- Real-time dashboard showing tool calls, errors, latency and client details
- AI visibility: track what ChatGPT, Claude and Gemini say about your product
- MCP server integration for agents to query your analytics data
- SDKs for TypeScript, Python, Go, Rust, C#, Java, Swift and browsers
- Identifies silent agent failures hidden from logs and APM
- Never blocks request paths with background worker batching
- Weekly or daily AI reviews depending on plan
- Funnels, conversions and email alerts
| - Debug failing agent calls with full visibility into inputs, outputs, prompts and tokens
- Edit arguments and retry the real call
- Inject a result and skip the call entirely
- Visual canvas to design agents and generate code
- Replay runs as test cases without keys or cost
- Circuit: durable workflows that pause instead of fail
- Jack: convert OpenAPI specs to OAuth-protected MCP servers
- Works with Vercel AI SDK, Anthropic, OpenAI, LangGraph and Python
|
|---|
| What makes it different | - Only platform showing silent agent failures that return 200 OK status codes
- Covers six distinct data sources in one dashboard instead of scattered logs
- Agents can access dashboard via MCP server to self-fix their failures
- Installation takes five minutes with background worker approach never blocking request paths
- AI visibility shows what AI models actually say about your product with claim verification
| - Holds failing calls mid-execution so you can inspect and fix them without rerunning
- Local-first debugger that runs on your machine with no account needed
- Open source under MIT license
- Integrates with existing code in two lines
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 0 | 7 |
| Referring domains (Majestic) | 0 | 1 |